Training in progress, step 940, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc2ee489f47ea596b321bd7995f2bac7a52945490c14f0a6880ce6475d80ec2
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:498c9374220fd4c1941619dd583dcc81dcf9e09c8a8c7c45e3d9c9a0492d40c8
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8891a0f6c9651643dc673aa37b083ae9f9a5618485ed2fa5e42864224aba8ac
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c75037f232440becd46b56e7118ddd0d9e982d54506ff3f4a917d7faef47618
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -948,6 +948,16 @@
|
|
| 948 |
"mean_token_accuracy": 0.778343915939331,
|
| 949 |
"num_tokens": 4336567.0,
|
| 950 |
"step": 930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 951 |
}
|
| 952 |
],
|
| 953 |
"logging_steps": 10,
|
|
@@ -967,7 +977,7 @@
|
|
| 967 |
"attributes": {}
|
| 968 |
}
|
| 969 |
},
|
| 970 |
-
"total_flos": 2.
|
| 971 |
"train_batch_size": 4,
|
| 972 |
"trial_name": null,
|
| 973 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.20053333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 948 |
"mean_token_accuracy": 0.778343915939331,
|
| 949 |
"num_tokens": 4336567.0,
|
| 950 |
"step": 930
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 0.8603343136608601,
|
| 954 |
+
"epoch": 0.20053333333333334,
|
| 955 |
+
"grad_norm": 0.22635255753993988,
|
| 956 |
+
"learning_rate": 9.878190490736353e-05,
|
| 957 |
+
"loss": 0.9547459602355957,
|
| 958 |
+
"mean_token_accuracy": 0.780703829228878,
|
| 959 |
+
"num_tokens": 4379939.0,
|
| 960 |
+
"step": 940
|
| 961 |
}
|
| 962 |
],
|
| 963 |
"logging_steps": 10,
|
|
|
|
| 977 |
"attributes": {}
|
| 978 |
}
|
| 979 |
},
|
| 980 |
+
"total_flos": 2.0759848815243264e+16,
|
| 981 |
"train_batch_size": 4,
|
| 982 |
"trial_name": null,
|
| 983 |
"trial_params": null
|